from automlk.dataset import get_dataset_list, create_dataset_sets
from automlk.store import list_key_store, set_key_store
"""
module specifically designed to update pp sampling results
"""
i = 0
for dt in get_dataset_list():
if dt.status != 'created' and dt.problem_type == 'classification':
print(dt.name)
results = list_key_store('dataset:%s:rounds' % dt.dataset_id)
set_key_store('dataset:%s:rounds_backup' % dt.dataset_id, results)
flag = False
for r in results:
pipeline = r['pipeline']
# print(pipeline)
sampling = [p for p in pipeline if p[1] == 'sampling']
if len(sampling) == 0:
print('missing sampling step')
r['pipeline'].append(('SP_PASS', 'sampling', 'No re-sampling', {}))
i += 1
flag = True
if flag:
set_key_store('dataset:%s:rounds' % dt.dataset_id, results)
print('modified pipelines:', i)
all_cat.append((c, pd.merge(best, counts, on='cat_ref').to_dict(orient='records')))
return all_cat
"""
def __select_cat(c, pipeline):
# select the element in the pipeline with category c
for p in pipeline:
if p[1] == c:
return p
return '', '', '', ''
for dt in get_dataset_list(include_results=True):
# check graph folders
if not os.path.exists(get_dataset_folder(dt.dataset_id) + '/graphs_dark'):
os.makedirs(get_dataset_folder(dt.dataset_id) + '/graphs_dark')
# generate best rounds
if dt.status != 'created':
print(dt.name)
# get search history
df = get_search_rounds(dt.dataset_id)
# generate graphs
best = __get_best_models(df)
best1 = best[best.level == 1]
best2 = best[best.level == 2]
graph_history_search(dt, df, best1, 1)
graph_history_search(dt, df, best2, 2)
def set_choices(self, problem_type):
self.dataset.choices = [(d.dataset_id, '#%s: %s' % (d.dataset_id, d.name)) for d in get_dataset_list() if d.problem_type == problem_type]
from automlk.dataset import get_data_folder, get_dataset_list
print('data folder:', get_data_folder())
print('list of datasets:', [d.name for d in get_dataset_list()])
from automlk.dataset import get_data_folder, get_dataset_list
print('data folder:', get_data_folder())
print('list of datasets:', get_dataset_list())
from automlk.store import *
from automlk.dataset import get_dataset_ids, get_dataset, get_dataset_list
print('dataset:counter', get_key_store('dataset:counter'))
print('dataset:list', list_key_store('dataset:list'))
print('dataset ids', get_dataset_ids())
dt = get_dataset(1)
print('dt ok')
l = get_dataset_list()